Hugging Face's logo

kokovova
/
11c561bd-fc4b-4cd2-af7c-6c97ffe633ba

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
kokovova commited on
Commit
3c8bba3
·
verified ·
1 Parent(s): 23df957

Training in progress, step 75, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +187 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ae275a5d593847471da51ddbf95ee47dc795cb5d50da9d179bbffe093604b45
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb78c6495c43b70406de794d7260c0fdd9be8879ecb59f0f1b864219b1352171
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ae1c8b35c043691704e73b10234ab2aeffc45287c0c7e0d309e1505148642f
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38e06c680080758d4c480bf60807616e8407c337f2411a730be80e96821dc820
3
  size 671466706
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3dc5fd93b9b05230499931de5440078d246a5022cd07a79303d2793ff0bce7b6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff9b9350a5fbca77fb4a1e3c294cd41d9a72b63ac4cc3e7f1197d70d20d94d0b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.21152829190904285,
5
  "eval_steps": 25,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -381,6 +381,189 @@
381
  "eval_samples_per_second": 8.962,
382
  "eval_steps_per_second": 4.504,
383
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
384
  }
385
  ],
386
  "logging_steps": 1,
@@ -395,12 +578,12 @@
395
  "should_evaluate": false,
396
  "should_log": false,
397
  "should_save": true,
398
- "should_training_stop": false
399
  },
400
  "attributes": {}
401
  }
402
  },
403
- "total_flos": 7.46010452164608e+16,
404
  "train_batch_size": 2,
405
  "trial_name": null,
406
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.31729243786356426,
5
  "eval_steps": 25,
6
+ "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
381
  "eval_samples_per_second": 8.962,
382
  "eval_steps_per_second": 4.504,
383
  "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.2157588577472237,
387
+ "grad_norm": 0.1405401974916458,
388
+ "learning_rate": 2.500000000000001e-05,
389
+ "loss": 0.1114,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.21998942358540455,
394
+ "grad_norm": 0.10868234187364578,
395
+ "learning_rate": 2.3135019582658802e-05,
396
+ "loss": 0.1065,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.2242199894235854,
401
+ "grad_norm": 0.11740752309560776,
402
+ "learning_rate": 2.132117818244771e-05,
403
+ "loss": 0.143,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.22845055526176627,
408
+ "grad_norm": 0.16673767566680908,
409
+ "learning_rate": 1.9561928549563968e-05,
410
+ "loss": 0.1385,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.23268112109994712,
415
+ "grad_norm": 0.1313553750514984,
416
+ "learning_rate": 1.7860619515673033e-05,
417
+ "loss": 0.1416,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.23691168693812797,
422
+ "grad_norm": 0.22419168055057526,
423
+ "learning_rate": 1.622048961921699e-05,
424
+ "loss": 0.1657,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.24114225277630882,
429
+ "grad_norm": 0.12620574235916138,
430
+ "learning_rate": 1.4644660940672627e-05,
431
+ "loss": 0.1182,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.2453728186144897,
436
+ "grad_norm": 0.0984712690114975,
437
+ "learning_rate": 1.3136133159493802e-05,
438
+ "loss": 0.122,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.24960338445267055,
443
+ "grad_norm": 0.12404455244541168,
444
+ "learning_rate": 1.1697777844051105e-05,
445
+ "loss": 0.1278,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.25383395029085143,
450
+ "grad_norm": 0.1908160299062729,
451
+ "learning_rate": 1.0332332985438248e-05,
452
+ "loss": 0.1428,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.25806451612903225,
457
+ "grad_norm": 0.17151938378810883,
458
+ "learning_rate": 9.042397785550405e-06,
459
+ "loss": 0.1438,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.26229508196721313,
464
+ "grad_norm": 0.14736545085906982,
465
+ "learning_rate": 7.830427709355725e-06,
466
+ "loss": 0.141,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.26652564780539395,
471
+ "grad_norm": 0.0722377598285675,
472
+ "learning_rate": 6.698729810778065e-06,
473
+ "loss": 0.1283,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.27075621364357483,
478
+ "grad_norm": 0.14723365008831024,
479
+ "learning_rate": 5.649458341088915e-06,
480
+ "loss": 0.1441,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.2749867794817557,
485
+ "grad_norm": 0.2239135503768921,
486
+ "learning_rate": 4.684610648167503e-06,
487
+ "loss": 0.1696,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 0.2792173453199365,
492
+ "grad_norm": 0.12539656460285187,
493
+ "learning_rate": 3.8060233744356633e-06,
494
+ "loss": 0.1273,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 0.2834479111581174,
499
+ "grad_norm": 0.14846888184547424,
500
+ "learning_rate": 3.0153689607045845e-06,
501
+ "loss": 0.1552,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 0.2876784769962983,
506
+ "grad_norm": 0.1942921280860901,
507
+ "learning_rate": 2.314152462588659e-06,
508
+ "loss": 0.1507,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 0.2919090428344791,
513
+ "grad_norm": 1.0786352157592773,
514
+ "learning_rate": 1.70370868554659e-06,
515
+ "loss": 0.1681,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 0.29613960867266,
520
+ "grad_norm": 0.1428898423910141,
521
+ "learning_rate": 1.1851996440033319e-06,
522
+ "loss": 0.1282,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 0.3003701745108408,
527
+ "grad_norm": 0.17222754657268524,
528
+ "learning_rate": 7.596123493895991e-07,
529
+ "loss": 0.1281,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 0.3046007403490217,
534
+ "grad_norm": 0.12844932079315186,
535
+ "learning_rate": 4.277569313094809e-07,
536
+ "loss": 0.1478,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 0.30883130618720256,
541
+ "grad_norm": 0.1278412789106369,
542
+ "learning_rate": 1.9026509541272275e-07,
543
+ "loss": 0.1369,
544
+ "step": 73
545
+ },
546
+ {
547
+ "epoch": 0.3130618720253834,
548
+ "grad_norm": 0.23847945034503937,
549
+ "learning_rate": 4.7588920907110094e-08,
550
+ "loss": 0.1768,
551
+ "step": 74
552
+ },
553
+ {
554
+ "epoch": 0.31729243786356426,
555
+ "grad_norm": 0.1610560566186905,
556
+ "learning_rate": 0.0,
557
+ "loss": 0.1589,
558
+ "step": 75
559
+ },
560
+ {
561
+ "epoch": 0.31729243786356426,
562
+ "eval_loss": 0.15878306329250336,
563
+ "eval_runtime": 22.1981,
564
+ "eval_samples_per_second": 8.965,
565
+ "eval_steps_per_second": 4.505,
566
+ "step": 75
567
  }
568
  ],
569
  "logging_steps": 1,
 
578
  "should_evaluate": false,
579
  "should_log": false,
580
  "should_save": true,
581
+ "should_training_stop": true
582
  },
583
  "attributes": {}
584
  }
585
  },
586
+ "total_flos": 1.119015678246912e+17,
587
  "train_batch_size": 2,
588
  "trial_name": null,
589
  "trial_params": null